eliancode (@eliancodex) header
eliancode (@eliancodex) profile picture

https://nitter.cf/t.co/tN2bg09zl5

Germany
Joined July 2025
Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)Photo by eliancode (@eliancodex)
GPT-6 Astra is the new #1 on BoardBench. It scores 67.2 vs the previous SOTA Gemini 4 Argon at 66.3. But it costs 2x as much ($0.56 per puzzle vs $0.28) for less than one point! Check it out at boardbench.dev
1
5
1,007
this is unfair i used all my limits on only 10x subsidization😂 you're gonna make me buy another go plan, right?
our inference team just came up to me and said they figured out how to give $300 of deepseek for $10
5
true if not rich
Prediction: smaller models will start outperforming bigger models
6
218
eliancode retweeted
AA's time per task completely ignores: - # of tool calls - ttft latency between tool calls - how long the tool calls take to run
2
1
19
1,989
100 followers🥳
2
1
12
235
Insane stuff.
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
1
54
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
2,312
7,226
5,550
55,225
9,081,468
wait you're telling me this wasn't a thing before?💀
Message threads are now in public beta on the Messages API. The API caches your conversation on the server between turns, so instead of resending the full conversation, you send only new messages and the previous message ID, and Claude starts responding sooner.
3
333
Claude is reverse engineering for me rn if u want the technique dm me
3
205
I should start telling people how good the next week in AI will be for likes.
2
3
199
this guy's a legend
Replying to @wshxnv
I'd rather give it out for free and find a way to charge enterprises in the future for bespoke things they uniquely need :)
1
31
HE DELETED IT😂😂😂
no shit sherlock! let me tell you something: the next 100 years will be crazy!
1
17
lmao Opus is happy to assist Deepseek with reverse engineering! it just wont do it itsself
53
30
5
2,688
69,562
no shit sherlock! let me tell you something: the next 100 years will be crazy!
This quoted post is unavailable.
1
1
27
sorry @sama but I need my 64gigs of ram to run a few hundred subagents to reverse engineer starcraft
1
5
124
eliancode retweeted
Replying to @davegoldblatt
"Hi Claude good morning how are you I'm great thx build me a YouTube-style site but restricted to videos that have been repeatedly recommended on HN over the years pls. Don't make any mistakes."
83
116
106
2,654
198,716
roon
I think roon is constantly searching his name as he always finds every mention of him
1
1
8
362
okay I'm beating it now, hold on
Day 28/ tibo's game has landed i spent $5.99 on this domain, but i had a blast making it with grok bot and cursor! i hope you enjoy it and find all the easter eggs 🤍 if i did it right you should be able to play it inside of X too tibo.dog
3
67